Class-Incremental Domain Adaptation

We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data but fail under a domain-shift without labeled supervision. In this work, we effectively identify the limitations of these approaches in the CIDA paradigm. Motivated by theoretical and empirical observations, we propose an effective method, inspired by prototypical networks, that enables classification of target samples into both shared and novel (one-shot) target classes, even under a domain-shift. Our approach yields superior performance as compared to both DA and CI methods in the CIDA paradigm.

[1]  Yoshua Bengio,et al.  Semi-supervised Learning by Entropy Minimization , 2004, CAP.

[2]  Koby Crammer,et al.  Learning from Multiple Sources , 2006, NIPS.

[3]  R. Venkatesh Babu,et al.  UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Zhihao Zheng,et al.  Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks , 2018, NeurIPS.

[5]  Eric P. Xing,et al.  Domain Adaption in One-Shot Learning , 2018, ECML/PKDD.

[6]  Stefan Rüping,et al.  Incremental Learning with Support Vector Machines , 2001, ICDM.

[7]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Kate Saenko,et al.  VisDA: The Visual Domain Adaptation Challenge , 2017, ArXiv.

[9]  Cordelia Schmid,et al.  End-to-End Incremental Learning , 2018, ECCV.

[10]  Kibok Lee,et al.  Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples , 2017, ICLR.

[11]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Dong-Hyun Lee,et al.  Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks , 2013 .

[13]  R. Venkatesh Babu,et al.  AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Alexander Zien,et al.  Semi-Supervised Classification by Low Density Separation , 2005, AISTATS.

[15]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[16]  Jianmin Wang,et al.  Transferable Curriculum for Weakly-Supervised Domain Adaptation , 2019, AAAI.

[17]  Koby Crammer,et al.  Analysis of Representations for Domain Adaptation , 2006, NIPS.

[18]  Tatsuya Harada,et al.  Maximum Classifier Discrepancy for Unsupervised Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[19]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[20]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[21]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Fei-Fei Li,et al.  Label Efficient Learning of Transferable Representations acrosss Domains and Tasks , 2017, NIPS.

[24]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jianxin Li,et al.  Incrementally Learning the Hierarchical Softmax Function for Neural Language Models , 2017, AAAI.

[27]  Bohyung Han,et al.  Domain-Specific Batch Normalization for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Rama Chellappa,et al.  Learning Without Memorizing , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Stanislav Fort,et al.  Gaussian Prototypical Networks for Few-Shot Learning on Omniglot , 2017, ArXiv.

[30]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[31]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[32]  Tom Drummond,et al.  Learning Factorized Representations for Open-set Domain Adaptation , 2018, ICLR.

[33]  R. Venkatesh Babu,et al.  Zero-Shot Knowledge Distillation in Deep Networks , 2019, ICML.

[34]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[35]  Jianmin Wang,et al.  Multi-Adversarial Domain Adaptation , 2018, AAAI.

[36]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.

[37]  Michael I. Jordan,et al.  Unsupervised Domain Adaptation with Residual Transfer Networks , 2016, NIPS.

[38]  R. Venkatesh Babu,et al.  GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[39]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[40]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

[41]  Thad Starner,et al.  Data-Free Knowledge Distillation for Deep Neural Networks , 2017, ArXiv.

[42]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.

[43]  Michael I. Jordan,et al.  Universal Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Alexei A. Efros,et al.  Undoing the Damage of Dataset Bias , 2012, ECCV.

[45]  Masashi Sugiyama,et al.  Unsupervised Domain Adaptation Based on Source-guided Discrepancy , 2018, AAAI.

[46]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[47]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[49]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[50]  Yandong Guo,et al.  Large Scale Incremental Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Yoshua Bengio,et al.  An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks , 2013, ICLR.

[52]  Hong Liu,et al.  Separate to Adapt: Open Set Domain Adaptation via Progressive Separation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[53]  Geoffrey E. Hinton,et al.  Regularizing Neural Networks by Penalizing Confident Output Distributions , 2017, ICLR.

[54]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[55]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[56]  Tatsuya Harada,et al.  Open Set Domain Adaptation by Backpropagation , 2018, ECCV.

[57]  Carlos D. Castillo,et al.  Generate to Adapt: Aligning Domains Using Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[58]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[59]  Juergen Gall,et al.  Open Set Domain Adaptation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[60]  R. Venkatesh Babu,et al.  Universal Source-Free Domain Adaptation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[61]  R. Venkatesh Babu,et al.  Towards Inheritable Models for Open-Set Domain Adaptation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).